Educational Applications for Blind and Partially Sighted Pupils Based on Speech Technologies for Serbian.
ABSTRACT: The inclusion of persons with disabilities has always represented an important issue. Advancements within the field of computer science have enabled the development of different types of aids, which have significantly improved the quality of life of the disabled. However, for some disabilities, such as visual impairment, the purpose of these aids is to establish an alternative communication channel and thus overcome the user's disability. Speech technologies play the crucial role in this process. This paper presents the ongoing efforts to create a set of educational applications based on speech technologies for Serbian for the early stages of education of blind and partially sighted children. Two educational applications dealing with memory exercises and comprehension of geometrical shapes are presented, along with the initial tests results obtained from research including visually impaired pupils.
Project description:OBJECTIVE:The aims of our study were to translate the dysfunctional voiding symptom score (DVSS) from English to Serbian; culturally adopt the items; assess the internal consistency and the test?retest reliability of DVSSSR in patients with dysfunctional voiding (DV); evaluate and test the construct and divergent validity of DVSSSR against demographic parameters (gender and education); and examine the level of explained variability for each item of DVSSSR against demographic parameters (gender and education). METHODS:The cross-sectional observational study included 50 patients with dysfunctional voiding aged 5 years and above. The DVSS questionnaire was translated from English into Serbian by the forward?backward method. Internal consistency was assessed with Cronbach ? and test?retest reliability with intraclass correlation coefficient (ICC). For validity testing we performed construct and divergent validity analyses. RESULTS:There was excellent internal consistency for every item except for Item 6 (0.787) and Item 3 (0.864), where internal consistency was good. The observed test/retest ICC for average measures was more than 0.75 (excellent) for all DVSSSR items. Gender and educational level does not correlate significantly with each item of DVSSSR (p > 0.05). For divergent validity, there were no significant differences in mean values of each item of DVSSSR between genders and different levels of education (p > 0.05). Variability that can be explained for gender and educational level was below 10%. CONCLUSION:Translated DVSSSR is of adequate validity and reliability for assessing DV in children.
Project description:Blind people are known to have superior perceptual abilities in their remaining senses. Several studies suggest that these enhancements are dependent on the specific experience of blind individuals, who use those remaining senses more than sighted subjects. In line with this view, sighted subjects, when trained, are able to significantly progress in relatively simple tactile tasks. However, the case of complex tactile tasks is less obvious, as some studies suggest that visual deprivation itself could confer large advantages in learning them. It remains unclear to what extent those complex skills, such as braille reading, can be learnt by sighted subjects. Here we enrolled twenty-nine sighted adults, mostly braille teachers and educators, in a 9-month braille reading course. At the beginning of the course, all subjects were naive in tactile braille reading. After the course, almost all were able to read whole braille words at a mean speed of 6 words-per-minute. Subjects with low tactile acuity did not differ significantly in braille reading speed from the rest of the group, indicating that low tactile acuity is not a limiting factor for learning braille, at least at this early stage of learning. Our study shows that most sighted adults can learn whole-word braille reading, given the right method and a considerable amount of motivation. The adult sensorimotor system can thus adapt, to some level, to very complex tactile tasks without visual deprivation. The pace of learning in our group was comparable to congenitally and early blind children learning braille in primary school, which suggests that the blind's mastery of complex tactile tasks can, to a large extent, be explained by experience-dependent mechanisms.
Project description:The three-dimensional micro-structure of physical surfaces produces frictional forces that provide sensory cues about properties of felt surfaces such as roughness. This tactile information activates somatosensory cortices, and frontal and temporal brain regions. Recent advances in haptic-feedback technologies allow the simulation of surface micro-structures via electro-static friction to produce touch sensations on otherwise flat screens. These sensations may benefit those with visual impairment or blindness. The primary aim of the current study was to test blind and sighted participants' perceptual sensitivity to simulated tactile gratings. A secondary aim was to explore which brain regions were involved in simulated touch to further understand the somatosensory brain network for touch. We used a haptic-feedback touchscreen which simulated tactile gratings using digitally manipulated electro-static friction. In Experiment 1, we compared blind and sighted participants' ability to detect the gratings by touch alone as a function of their spatial frequency (bar width) and intensity. Both blind and sighted participants showed high sensitivity to detect simulated tactile gratings, and their tactile sensitivity functions showed both linear and quadratic dependency on spatial frequency. In Experiment 2, using functional magnetic resonance imaging, we conducted a preliminary investigation to explore whether brain activation to physical vibrations correlated with blindfolded (but sighted) participants' performance with simulated tactile gratings outside the scanner. At the neural level, blindfolded (but sighted) participants' detection performance correlated with brain activation in bi-lateral supplementary motor cortex, left frontal cortex and right occipital cortex. Taken together with previous studies, these results suggest that there are similar perceptual and neural mechanisms for real and simulated touch sensations.
Project description:Serbian is in a group of highly inflective and morphologically rich languages that use a lot of different word suffixes to express different grammatical, syntactic, or semantic features. This kind of behaviour usually produces a lot of recognition errors, especially in large vocabulary systems-even when, due to good acoustical matching, the correct lemma is predicted by the automatic speech recognition system, often a wrong word ending occurs, which is nevertheless counted as an error. This effect is larger for contexts not present in the language model training corpus. In this manuscript, an approach which takes into account different morphological categories of words for language modeling is examined, and the benefits in terms of word error rates and perplexities are presented. These categories include word type, word case, grammatical number, and gender, and they were all assigned to words in the system vocabulary, where applicable. These additional word features helped to produce significant improvements in relation to the baseline system, both for n-gram-based and neural network-based language models. The proposed system can help overcome a lot of tedious errors in a large vocabulary system, for example, for dictation, both for Serbian and for other languages with similar characteristics.
Project description:How does first-person sensory experience contribute to knowledge? Contrary to the suppositions of early empiricist philosophers, people who are born blind know about phenomena that cannot be perceived directly, such as color and light. Exactly what is learned and how remains an open question. We compared knowledge of animal appearance across congenitally blind (n = 20) and sighted individuals (two groups, n = 20 and n = 35) using a battery of tasks, including ordering (size and height), sorting (shape, skin texture, and color), odd-one-out (shape), and feature choice (texture). On all tested dimensions apart from color, sighted and blind individuals showed substantial albeit imperfect agreement, suggesting that linguistic communication and visual perception convey partially redundant appearance information. To test the hypothesis that blind individuals learn about appearance primarily by remembering sighted people's descriptions of what they see (e.g., "elephants are gray"), we measured verbalizability of animal shape, texture, and color in the sighted. Contrary to the learn-from-description hypothesis, blind and sighted groups disagreed most about the appearance dimension that was easiest for sighted people to verbalize: color. Analysis of disagreement patterns across all tasks suggest that blind individuals infer physical features from non-appearance properties of animals such as folk taxonomy and habitat (e.g., bats are textured like mammals but shaped like birds). These findings suggest that in the absence of sensory access, structured appearance knowledge is acquired through inference from ontological kind.
Project description:<h4>Purpose</h4>The study aim was to translate and validate the Glaucoma Symptom Scale (GSS) in Serbian language.<h4>Methods</h4>Clinical parameters and socio-demographic data were collected for each of the 177 enrolled glaucoma patients. Each eye was classified according to the Glaucoma staging system by Mills into 6 stages. Patients filled out the GSS and National Eye Institute Visual Function Questionnaire (NEI-VFQ 25). The GSS comprises 10 complaints common for glaucoma patients on a topical treatment, grouped into two subscales: SYMP-6 (non-visual) and FUNC-4 (visual problems). The GSS was translated following the customary methodology and its psychometric properties were assessed by using both Classical Test Theory (CTT) and Rasch analysis.<h4>Results</h4>The internal consistency of the Serbian GSS for the whole scale was very good (Cronbach's alpha = 0.81). On factor analysis items were clustered into 2 factors (48.92% of variance) which corresponded to the original scale. The total and subscale GSS scores correlated significantly with measures of disease severity and also with total score and analogous NEI-VFQ 25 subscale scores. In Rasch analysis we obtained adequate item reliability index (0.90). Almost all items had infit and outfit mean squares in the accepted range. However, measurement precision was poor (low person separation reliability) and targeting revealed a ceiling effect.<h4>Conclusion</h4>When analyzed with CTT the Serbian version of the GSS seems to be a valid instrument, but Rasch analysis revealed some serious measurement flaws, therefore it should not be used in its current format. Further studies to modify and improve GSS are needed prior to its application for Serbian glaucoma patients.
Project description:Some blind people have developed a unique technique, called echolocation, to orient themselves in unknown environments. More specifically, by self-generating a clicking noise with the tongue, echolocators gain knowledge about the external environment by perceiving more detailed object features. It is not clear to date whether sighted individuals can also develop such an extremely useful technique. To investigate this, here we test the ability of novice sighted participants to perform a depth echolocation task. Moreover, in order to evaluate whether the type of room (anechoic or reverberant) and the type of clicking sound (with the tongue or with the hands) influences the learning of this technique, we divided the entire sample into four groups. Half of the participants produced the clicking sound with their tongue, the other half with their hands. Half of the participants performed the task in an anechoic chamber, the other half in a reverberant room. Subjects stood in front of five bars, each of a different size, and at five different distances from the subject. The dimension of the bars ensured a constant subtended angle for the five distances considered. The task was to identify the correct distance of the bar. We found that, even by the second session, the participants were able to judge the correct depth of the bar at a rate greater than chance. Improvements in both precision and accuracy were observed in all experimental sessions. More interestingly, we found significantly better performance in the reverberant room than in the anechoic chamber. The type of clicking did not modulate our results. This suggests that the echolocation technique can also be learned by sighted individuals and that room reverberation can influence this learning process. More generally, this study shows that total loss of sight is not a prerequisite for echolocation skills this suggests important potential implications on rehabilitation settings for persons with residual vision.
Project description:Is vision necessary for the development of the categorical organization of the Ventral Occipito-Temporal Cortex (VOTC)? We used fMRI to characterize VOTC responses to eight categories presented acoustically in sighted and early blind individuals, and visually in a separate sighted group. We observed that VOTC reliably encodes sound categories in sighted and blind people using a representational structure and connectivity partially similar to the one found in vision. Sound categories were, however, more reliably encoded in the blind than the sighted group, using a representational format closer to the one found in vision. Crucially, VOTC in blind represents the categorical membership of sounds rather than their acoustic features. Our results suggest that sounds trigger categorical responses in the VOTC of congenitally blind and sighted people that partially match the topography and functional profile of the visual response, despite qualitative nuances in the categorical organization of VOTC between modalities and groups.
Project description:Although evidence is mixed, studies have shown that blind individuals perform better than sighted at specific auditory, tactile, and chemosensory tasks. However, few studies have assessed blind and sighted individuals across different sensory modalities in the same study. We tested early blind (n = 15), late blind (n = 15), and sighted (n = 30) participants with analogous olfactory and auditory tests in absolute threshold, discrimination, identification, episodic recognition, and metacognitive ability. Although the multivariate analysis of variance (MANOVA) showed no overall effect of blindness and no interaction with modality, follow-up between-group contrasts indicated a blind-over-sighted advantage in auditory episodic recognition, that was most pronounced in early blind individuals. In contrast to the auditory modality, there was no empirical support for compensatory effects in any of the olfactory tasks. There was no conclusive evidence for group differences in metacognitive ability to predict episodic recognition performance. Taken together, the results showed no evidence of an overall superior performance in blind relative sighted individuals across olfactory and auditory functions, although early blind individuals exceled in episodic auditory recognition memory. This observation may be related to an experience-induced increase in auditory attentional capacity.
Project description:BACKGROUND:Steroid 21-hydroxylase deficiency is present in 90-95% of all cases with congenital adrenal hyperplasia (CAH), an autosomal recessive disorder. It can present as the severe classical salt wasting (SW) or simple virilising (SV) form, or the milder, nonclassical form. Nine pseudogene-derived point mutations account for about 80% of all defects in the CYP21A2 gene coding the 21-hydroxylase enzyme. METHODS:We have studied nine CYP21A2 point mutations in 61 Macedonian and 24 Serbian patients with different clinical presentations of CAH, using the PCR/ACRS method. RESULTS:Six different mutations were detected in 71.3% of alleles of the Macedonian patients. The most prevalent mutation was IVS2. Mutations were detected in 85.4% of the SW, 83.4% SV and 47.7% LO alleles. In the Macedonian patients the most common genotype was IVS2/IVS2. Five different mutations were detected in 64.6% of alleles of the Serbian patients. The most prevalent was P30L. Mutations were present in 83.3% SW, 80% SV and 50% of the LO alleles. In the Serbian patients, the P30L/P30L genotype was the most frequent. CONCLUSIONS:Specific CYP21A2 mutations are involved in different clinical forms of CAH. High frequency of P30L was found in both populations. Also, high prevalence of the mild P30L mutation was found in both the Macedonian and Serbian classical SV patients. Our findings support the role of the P30L mutation in pronounced virilisation. An unusual finding is the low frequency of V281L in the Macedonian non-classical patients and its absence in the ones from Serbia.